Quant Methods For Business

Next to examine the relationship between shopping expenditures and consumer characteristics – specifically income, age and marital status using the data below. You want to see how each variable is related to expenditures, the ability of each variable to explain variations in spending and the effect of marital status, if any, upon spending.

	Shopping Expenditure	Income	Age	Married (1=Yes, 0=No)
1	410	55	44	1
2	551	62	36	1
3	677	102	51	1
4	1120	225	49	0
5	325	48	34	0
6	334	32	28	1
7	200	26	24	0
8	400	44	36	1
9	648	98	42	1
10	550	72	50	1
11	350	55	36	0
12	375	63	27	0
13	149	18	19	0
14	475	62	35	1
15	350	55	43	0
16	298	40	29	1
17	235	33	24	0
18	580	99	52	0
19	1600	304	62	1
20	740	115	54	1
21	1180	203	58	1
22	500	88	43	0
23	445	55	32	1
24	278	42	30	0
25	115	26	25	0
26	456	73	34	1
27	189	21	20	0
28	455	38	33	1
29	302	39	25	0
30	255	36	29	1
31	168	41	31	1
32	255	29	23	0
33	315	37	33	1
34	730	116	42	1
35	552	69	44	1
36	488	84	30	0
37	545	77	36	1
38	750	145	34	0
39	545	66	55	1
40	499	70	53	1
41	602	82	46	1
42	488	51	39	1
43	415	49	31	1
44	444	66	38	0
45	322	34	26	1
46	145	22	21	0
47	111	19	22	0
48	810	155	38	0
49	1205	200	43	1
50	559	111	51	0

Using this data:

a. Generate a regression model to examine shopping expenditures. Explore all possible models, first using single independent variables (Xes) and then a multiple regression. Perform all appropriate analyses and hypothesis tests and then report your results in a memo and attach a statistical appendix detailing the hypothesis testing and other procedures that you have used in the analysis.

b. Select the best model and explain what the coefficients mean.

6